在半導體與TFT-LCD產業應用虛擬量測系統時，由取得生產機台之參數資料後，則可即時預測晶圓或玻璃之產品品質，以達成即時逐片檢測品質的目標。虛擬量測系統的關鍵在於產生即時且準確的虛擬量測值，選擇具精確與快速之預測模型是非常重要的課題。本研究採用的通用迴歸類神經網路，該網路具有無初始隨機權重的優勢，不需重覆多次實驗即可得到客觀結果。而在建構模型時僅需設定一平滑參數，選擇一個適當大小的平滑參數即可產生較佳之預測效果。為了評估通用迴歸類神經網路之適用性，利用半導體與TFT-LCD廠的實際案例，將對於參數篩選之必要性，SRNN、BPNN-I和GRNN精度之比較，以及GRNN應用於不同產品線上的換模機制等三項議題進行實驗與探討。由實驗證明運用通用迴歸類神經網路建構之虛擬量測模型，能達成良好的預測精度和提升預測效率。

In the semiconductor and TFT-LCD industries, virtual metrology system (VMS) can measure the quality of wafer or glass right after the process data is collected, and thus can reach the goal of real time wafer-to-wafer quality examination. The key of VMS is to generate real-time and accurate conjecture results. Therefore, how to construct an accurate and fast conjecture model is an important issue. In this research, the general regression neural network (GRNN) is adopted to construct the virtual metrology (VM) model. Lacking the influence of initial random weights, the GRNN only requires adequate smooth parameters to generate better conjecture values and more objective conjecture results without repetitive experiments. In order to evaluate the applicability of GRNN in the semiconductor and TFT-LCD industries, experiments and case studies are made to discuss issues including the necessity of parameter sifting, the precision comparison of among SRNN, BPNN-I and GRNN, and the application of GRNN in model refreshing. Experiment results show that better conjecture accuracy and conjecture efficiency can be achieved by using GRNN to construct VM models.

[1] A.C. Diebold, “Overview of metrology requirements based on the 1994 national technology roadmap for semiconductor,” in Proc. of IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop, pp. 50-60, Nov. 1995.
[2] 2003 International Technology Roadmap for Semiconductors (ITRS), Dec. 2003. http://public.itrs.net/
[3] P.-H. Chen, S. Wu, J.-S. Lin, F. Ko, H. Lo, J. Wang, C.-H. Yu, and M.-S. Liang, “Virtual Metrology: a Solution for Wafer to Wafer Advanced Process Control,” in Proc. 2005 IEEE International Symposium on Semiconductor Manufacturing, San Jose, CA, pp. 155-157, Sept. 2005.
[4] Y.-C. Su, M.-H. Hung, F.-T. Cheng and Y.-T. chen, “ A processing quality prognostics scheme for plasma sputtering in TFT-LCD manufacturing,”IEEE Transactions on Semiconductor Manufacturing , vol. 19, issue 2 , pp. 183-194, 2006.
[5] Y.-C. Su, F.-T. Cheng, M.-H. Hung, and H.-C. Huang, “Intelligent Prognostics System Designand and
Implementation,” IEEE Transactions on Semiconductor Manufacturing, vol. 19, no. 2, pp. 195-207, May 2006.
[6] Y.-J. Chang, Y. Kang, C.-L. Hsu, C.-T. Chang, and T. Y. Chan, “Virtual Metrology Technique for Semiconductor Manufacturing,” in Proc. 2006 International Joint Conference on Neural Networks, pp. 5289-5293, July 2006.
[7] M.-H. Hung, T.-H. Lin, F.-T. Cheng, and R.-C. Lin, “A novel virtual metrology scheme for predicting CVD thickness in semiconductor manufacturing,” IEEE/ASME Transactions on Mechatronics, vol. 12, no. 3, pp. 308-316, June 2007.
[8] Y.-T. Huang, H.-C. Huang, F.-T. Cheng, and T.-S. Liao, and F.-C. Chang, “Automatic Virtual Metrology System Design and Implementation,” in Proc. IEEE International Conference on Automation Science and Engineering,
Washington, D.C., U.S.A., August 2008.
[9] Y.-C. Su, T.-H. Lin, F.-T. Cheng, and W.-M. Wu, "Implementation considerations of various virtual metrology algorithms," in Proc. 2007 IEEE International Conference on Automation Science and Engineering, Scottsdale, Arizona, U.S.A., pp.276-281, Sept. 2007.
[10] S. Huang, and H. Zhang, “”Neural Network in Manufacturing:A Survey,” IEEE/CPMT International Electronics Manufacturing Technology
Symposium”, pp.177-190, 1993.
[11] 葉怡成「應用類神經網路」，儒林圖書公司，1997.
[12] 葉怡成「類神經網路模式應用與實作」，儒林圖書公司，2003.
[13] J. L. Elman, “Finding Structure in Time,” Cognitive Science, vol. 14, pp. 179-211, 1990.
[14] Donald F. Specht, “A General Regression Neural Network,” IEEE Transactions on Neural Network, vol. 2, no. 6, pp. 568-576, Nov. 1991.
[15] T.-H. Lin, F.-T. Cheng, A.-J. Ye, W.-M. Wu, and M.-H. Hung "A novel key-variable sifting algorithm for virtual metrology," in Proc. 2008 IEEE International Conference on Robotics and Automation, Pasadena, California,
U.S.A., May 2008.
[16] I. H. Witten and E. Frank, Data Mining: Practical Machine Learning Tools and Techniques, San Francisco, CA: Morgan Kaufman, 2005.
[17] 陳順宇 「多變量分析」，四版，華泰書局，2004.